Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    czą
    0.54
     oppress
    0.50
    nang
    0.47
    ეგის
    0.46
     vínculos
    0.46
    cych
    0.45
    TypeCode
    0.45
     échange
    0.44
    ನ್ನು
    0.44
    응
    0.44
    POSITIVE LOGITS
     Dr
    0.43
     Mi
    0.43
     Cu
    0.42
     Training
    0.42
     Astronomy
    0.42
     Data
    0.41
     Inner
    0.41
     Ne
    0.41
     Te
    0.40
     La
    0.40
    Act Density 0.004%

    No Known Activations